Function find_robots

src/12/simple_parallel_programming/findrobots.py:7–17

Find all of the hosts that access robots.txt in a single log file

(filename)

import glob

def find_robots(filename):
    '''
    Find all of the hosts that access robots.txt in a single log file
    '''
    robots = set()
    with gzip.open(filename) as f:
        for line in io.TextIOWrapper(f,encoding='ascii'):
            fields = line.split()
            if fields[6] == '/robots.txt':
                robots.add(fields[0])
    return robots

def find_all_robots(logdir):
    '''